curAIvasc: AI-based analysis of vascular imaging for optimized multidimensional information assessment.

1 PhD position in the curATime clusters4future initiative offered in IPP winter call 2022

Scientific Background

Current methods of highly standardized subclinical phenotyping enable high-resolution characterization of people with atherothrombosis or the risk of developing atherothrombosis. However, despite all the advances in recent years, only a fraction (about 15%) of the potential of biodata is currently being used in clinical and research applications. One of the reasons for this is that the available information from multidimensional image data for the characterization of the arterial vascular system, which is centrally involved in the development of atherothrombosis, is currently not sufficiently used.

New developments in the field of artificial intelligence and deep learning open up the possibility of exploiting the previously untapped potential of clinically relevant information from different modalities of vascular imaging for in-depth clinical phenotyping. The AI-assisted characterization of vascular structure and function is an innovative approach to improve the precision of traditional measurements, both in terms of time efficiency and quality. A comprehensive approach that uses all information contained in vascular images represents a promising tool to transform the use of vascular image information across different imaging modalities.

PhD project: "curAIvasc"

This project is part of “CurATime – Cluster for Atherothrombosis and Individualized Medicine” (www.curatime.org), a research cluster recently announced to be funded by the German Federal Ministry of Education and Research (BMBF) for €15 million for the first 3-year funding period. The goal of the curAIvasc-project is to develop innovative technologies and AI pipelines for the analysis of multi-dimensional biodata on vascular function and structure and to transfer them to patient-oriented research on atherothrombosis. As part of this project your tasks would be:

  • In close collaboration with DFKI you will be implementing and using a multidimensional/multimodal deep learning (DL) pipeline for image-based prediction of individual disease progression and personalized risk assessment.

  • Evaluating the created pipeline based on the harmonized analysis concept in the biodatabases. For this purpose, state-of-the-art methods of biostatistical analysis will be used, evaluating the quality and medical relevance of the newly developed pipeline.

  • Application of the established AI pipeline for biomedical interpretation, which includes the integration of the information from the DL pipeline into high dimensional multi-omics data (e.g. proteomics, genetics).

The candidate will be integrated in a friendly, professional and highly multidisciplinary team, comprising clinicians, epidemiologists, bioinformaticians, biostatisticians, as well as biologists and biochemists. Specific competences and supervisors are present to support the PhD candidate. Within the curAIvasc project, the candidate will additionally interact with experts in the fields of artificial intelligence (DFKI, German Research Center for Artificial Intelligence), experimental research (Center for Thrombosis and Hemostasis Mainz) and biotechnology (TRON/BioNTech).

Publications relevant to this project

  • Tröbs SO, Prochaska JH, Schwuchow-Thonke S, Schulz A, Müller F, Heidorn MW, Göbel S, Diestelmeier S, Lerma Monteverde J, Lackner KJ, Gori T, Münzel T, Wild PS. Association of Global Longitudinal Strain With Clinical Status and Mortality in Patients With Chronic Heart Failure. JAMA Cardiol. 2021 Apr 1;6(4):448-456.

  • Prochaska JH, Arnold N, Falcke A, Kopp S, Schulz A, Buch G, Moll S, Panova-Noeva M, Jünger C, Eggebrecht L, Pfeiffer N, Beutel M, Binder H, Grabbe S, Lackner KJ, Ten Cate-Hoek A, Espinola-Klein C, Münzel T, Wild PS. Chronic venous insufficiency, cardiovascular disease, and mortality: a population study.Eur Heart J. 2021 Oct 21;42(40):4157-4165.

  • Ten Cate V, Prochaska JH, Schulz A, Koeck T, Pallares Robles A, Lenz M, Eggebrecht L, Rapp S, Panova-Noeva M, Ghofrani HA, Meyer FJ, Espinola-Klein C, Lackner KJ, Michal M, Schuster AK, Strauch K, Zink AM, Laux V, Heitmeier S, Konstantinides SV, Münzel T, Andrade-Navarro MA, Leineweber K, Wild PS. Protein expression profiling suggests relevance of noncanonical pathways in isolated pulmonary embolism. Blood. 2021 May 13;137(19):2681-2693.

  • Bajwa MN, Malik MI, Siddiqui SA, Dengel A, Shafait F, Neumeier W, Ahmed S. Two-stage framework for optic disc localization and glaucoma classification in retinal fundus images using deep learning.BMC Med Inform Decis Mak. 2019 Jul 17;19(1):136.

  • Muralidhara S, Lucieri A, Dengel A, Ahmed S. Holistic multi-class classification & grading of diabetic foot ulcerations from plantar thermal images using deep learning. Health Inf Sci Syst. 2022 Aug 26;10(1):21.

Contact Details

Dr. Jürgen Prochaska (primary contact)
Group leader, Clinical Epidemiology and Systems Medicine, Center for Thrombosis and Hemostasis, Mainz
Deputy Head of Preventive Cardiology, Senior Cardiologist
University Medical Center Mainz
Email    

Prof. Philipp S. Wild (senior supervisor)
Head, Clinical Epidemiology and Systems Medicine, Center for Thrombosis and Hemostasis, Mainz
Head, Preventive Cardiology and Medical Prevention, University Medical Center Mainz
Systems Medicine, Institute of Molecular Biology
Email